Surveillance of Super-Extended Objects: Bimodal Approach

This paper describes an effective solution to the task
of a remote monitoring of super-extended objects (oil and gas
pipeline, railways, national frontier). The suggested solution is based
on the principle of simultaneously monitoring of seismoacoustic and
optical/infrared physical fields. The principle of simultaneous
monitoring of those fields is not new but in contrast to the known
solutions the suggested approach allows to control super-extended
objects with very limited operational costs. So-called C-OTDR
(Coherent Optical Time Domain Reflectometer) systems are used to
monitor the seismoacoustic field. Far-CCTV systems are used to
monitor the optical/infrared field. A simultaneous data processing
provided by both systems allows effectively detecting and classifying
target activities, which appear in the monitored objects vicinity. The
results of practical usage had shown high effectiveness of the
suggested approach.

• Andrey V. Timofeev
• Dmitry Egorov

• Bimodal processing
• C-OTDR monitoring system
• LPboost
• SVM.

[1] M. Elhoseiny, A. Bakry, and A. Elgammal, "MultiClass Object
Classification in Video Surveillance Systems - Experimental Study”.
In Proceedings of the 2013 IEEE Conference on Computer Vision and
Pattern Recognition Workshops (CVPRW '13). IEEE Computer Society,
Washington, DC, USA, 2013, pp. 788-793.
[2] D. G. Lowe, "Distinctive image features from scale-invariant keypoints”.
IJCV, 60(2), 2014, pp.91–110.
[3] M. Tan, L. Wang, and I. W. Tsang, "Learning sparse svm for feature
selection on very high dimensional datasets”, ICML, 2010, pp. 1047-
1054.
[4] A. Bosch, A. Zisserman, and X. Muoz, "Scene classification using a
hybrid generative/discriminative approach,” IEEE Trans. Pattern
Analysis and Machine Intell, 30(04), 2008, pp.712-727.
[5] A. E. Abdel-Hakim and A. A. Farag"CSIFT: A SIFT Descriptor
with Color Invariant Characteristics,” Computer Vision and Image
Processing Laboratory. (CVPR'06), 2006, pp.1978-1983.
[6] I. Laptev, "On space-time interest points”, IJCV, 64(2-3), 2005, pp.107–
123.
[7] H. Wang, A. Klaser, C. Schmid, and C.-L. Liu, "Dense trajectories and
motion boundary descriptors for action recognition’, IJCV,103(1), 2013,
pp.60–79.
[8] P. Merlmestein and S. Davis, "Comparison of Parametric
Representations for Monosyllabic Word Recognition in Continuously.
Spoken Sentences”, IEEE Trans. On ASSP, Aug, 1980. pp. 357-366.
[9] D. Titterington, A. Smith, U. Makov, Statistical Analysis of Finite
Mixture Distributions. Wiley. ISBN 0-471-90763-4, 1985.
[10] M.A. Figueiredo, A.K. Jain, "Unsupervised Learning of Finite Mixture
Models", IEEE Transactions on Pattern Analysis and Machine
Intelligence 24 (3), 2002, pp.381–396.
[11] S. Belongie, J. Malik, and J. Puzicha. "Matching shapes”, The 8th ICCV,
Vancouver, Canada, pp. 454-461, 2001.
[12] Y. Ke and R. Sukthankar, "PCA-SIFT: A more distinctive representation
for local image descriptors”, CVPR, Washington, DC, USA, 2004, pp.
66-75.
[13] N. Dalal, B. Triggs, "Histograms of Oriented Gradients for Human
Detection," IEEE Computer Society Conference on Computer Vision and
Pattern Recognition (CVPR'05), vol. 1, 2005, pp.886-893.
[14] V. Gehler, and Sebastian Nowozin, "On feature combination for
multiclass object classification”, Peter. ICCV, IEEE, 2009, pp. 221-228.
[15] G. Ratsch, B. Scholkopf, A.J. Smola, S. Mika, T. Onoda, and K-R.
Muller, "Robust ensemble learning”, In A.J. Smola, P. L. Bartlett, B.
Scholkopf, and D. Schuurmans, editors, Advances in Large Margin
Classifiers, MIT Press, 1999, pр. 208–222.
[16] M.A. Hears, S.T. Dumais, E. Osman, J. Platt, and B. Scholkopf,
"Support Vector Machines”, IEEE Intelligent Systems, vol. 13(4), 1998,
pp.18-28.
[17] T. Jebara and R. Kondor, "Bhattacharyya and expected likelihood
kernels”, In Proc.16th Annual Conference on Learning Theory (COLT
2003), 2003.
[18] M. Stone, "Asymptotics for and against cross-validation”, Biometrika,
1977, 64 (1), pp. 29–35.